AlexNet
Deep convolutional network that won the 2012 ImageNet challenge and is widely cited as the spark of the modern deep-learning era.
AlexNet is the deep neural network built by Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton that won the 2012 ImageNet challenge by a wide margin. It combined a large labelled dataset, GPU training, ReLU activations, and dropout.
The result is often marked as the start of the modern deep learning boom in computer vision, and as early proof that learned features at scale can beat hand-designed ones. See the article and timeline for the full story.